Method and device for finding nearest neighbor

a technology of nearest neighbor and method, applied in the field of object clustering and identification in video, can solve the problems of large amount of memory, search algorithm sacrifices speed for memory space, and algorithm in any case requires a minimum of spa

Active Publication Date: 2013-09-26
IVISYS SWEDEN AB
View PDF2 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Benefits of technology

[0038]This aspect allows subsequent fast ma

Problems solved by technology

However, the algorithm in any case requires a minimum of space.
This requires large amounts

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Method and device for finding nearest neighbor
  • Method and device for finding nearest neighbor
  • Method and device for finding nearest neighbor

Examples

Experimental program
Comparison scheme
Effect test

example

[0143]This example concerns a method implementing an embodiment of the invention for high speed data vector matching by organizing and searching n-dimensional data vectors in memory elements. This method is useful for several applications, such as searches involving a multidimensional search key (e.g. range searches and nearest neighbor searches).This method relies on statically structuring reference data vectors in special memory constructions in a manner to speed up the search and matching with dynamically entered data vectors in real time.

[0144]This method and the invention potentially reduces the number of searches within a data base to find a match between data vectors to a factor of log2(size), wherein size is the size of the reference database in number of data vectors. This is illustrated in FIG. 1.

[0145]This method may be implemented in GPUs, DSPs and parallel processing hardware such as FPGAs and ASICs.

[0146]This method works by structuring reference data vectors in a spec...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The present invention relates to a method and a device for finding nearest neighbor. In particular, it relates to a sorting, searching and matching multiple dimensional data, such as vectors, in order to find the nearest neighbor. The method is particularly useful as part of a SIFT algorithm.

Description

[0001]The present invention relates to a method and a device for finding nearest neighbor. In particular, it relates to a sorting, searching and matching multiple dimensional data, such as vectors, in order to find the nearest neighbor. The method is particularly useful as part of a SIFT algorithm.TECHNICAL BACKGROUND[0002]Lowe, inventor of the U.S. Pat. No. 6,711,293 B1, used a modification of the k-d tree algorithm known as the Best-bin-first search method that can identify the nearest neighbors with high probability using only a limited amount of computation.[0003]US 2010 / 0067745 discloses a method for object clustering and identification in video. In particular, it concerns the identification of facial images. The method uses clusters of video objects which are likely associated with the same person. A new image is deemed to belong to an existing cluster if the distance to the cluster is smaller than a first predetermined threshold distance. The new image becomes part of the clu...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
IPC IPC(8): G06K9/62G06V10/764
CPCG06F17/30247G06K9/6267G06K9/6276G06K9/4671G06F16/583G06V10/462G06V10/764G06F18/24G06F18/24147
Inventor CHEHAIBER, MOATASEM
Owner IVISYS SWEDEN AB
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products